On limiting distributions in explosive autoregressive processes

DOI10.1016/S0167-7152(97)00111-9zbMath0909.62011MaRDI QIDQ1379906

Piotr W. Mikulski, Michael J. Monsour

Publication date: 8 April 1999

Published in: Statistics \& Probability Letters (Search for Journal in Brave)

zbMATH Keywords

characteristic roots; canonical form; Jordan normal; pure explosive autoregressive process

Mathematics Subject Classification ID

62M10: Time series, auto-correlation, regression, etc. in statistics (GARCH)

62E20: Asymptotic distribution theory in statistics

Related Items

Decomposition of an autoregressive process into first order processes, Sequential fixed accuracy estimation for nonstationary autoregressive processes, Explosive strong periodic autoregression with multiplicity one, Asymptotics of regressions with stationary and nonstationary residuals.

Cites Work

• Limiting distributions of least squares estimates of unstable autoregressive processes
• On the strong approximation of the distributions of estimators in linear stochastic models, I and II: Stationary and explosive AR models
• Estimation of the parameters of stochastic difference equations
• Asymptotic properties of dynamic stochastic parameter estimates. III
• Asymptotic properties of general autoregressive models and strong consistency of least-squares estimates of their parameters
• On Asymptotic Distributions of Estimates of Parameters of Stochastic Difference Equations
• Orthonormal Banach systems with applications to linear processes
• Matrix Analysis
• On the Statistical Treatment of Linear Stochastic Difference Equations